Using an extreme learning machine to predict the displacement of step-like landslides in relation to controlling factors

In the evolution of landslides, besides the geological conditions, displacement depends on the variation of the controlling factors. Due to the periodic fluctuation of the reservoir water level and the precipitation, the shape of cumulative displacement-time curves of the colluvial landslides in the Three Gorges Reservoir follows a step function. The Baijiabao landslide in the Three Gorges region was selected as a case study. By analysing the response relationship between the landslide deformation, the rainfall, the reservoir water level and the groundwater level, an extreme learning machine was proposed in order to establish the landslide displacement prediction model in relation to controlling factors. The result demonstrated that the curves of the predicted and measured values were very similar, with a correlation coefficient of 0.984. They showed a distinctive step-like deformation characteristic, which underlined the role of the influencing factors in the displacement of the landslide. In relation to controlling factors, the proposed extreme learning machine (ELM) model showed a great ability to predict the Baijiabao landslide and is thus an effective displacement prediction method for colluvial landslides with step-like deformation in the Three Gorges Reservoir region.     

基于多算法参数优化与SVR模型的白水河滑坡位移预测

滑坡预测对于减轻地质灾害的危害十分重要,但对科学研究却很有挑战性。基于变形特征和位移监测数据,建立了三峡库区白水河滑坡的时间序列加法模型。在模型中,累计位移分为3个部分:趋势、周期和随机项,解释了由内部因素（地质环境,重力等）、外部因素（降雨,水库水位等）、随机因素（不确定性）共同作用的影响。在对位移数据进行统计分析后,提出了一个3次多项式模型对趋势项进行学习,并利用多算法寻优的支持向量回归机（SVR）模型对周期项进行训练与预测。结果表明,在预测精度上,基于时间序列与遗传算法-支持向量回归机（GA-SVR）耦合的位移预测模型要明显优于网格寻优（GS）以及粒子群算法（PSO）优化的支持向量回归机模型。因此,GA-SVR模型在滑坡位移预测方面可以得到较好的应用。在“阶跃型”滑坡位移预测中,GA-SVR将具有广阔的应用前景。     

Displacement prediction of step-like landslide by applying a novel kernel extreme learning machine method

Landslide displacement prediction is an essential component for developing landslide early warning systems. In the Three Gorges Reservoir area (TGRA), landslides experience step-like deformations (i.e., periods of stability interrupted by abrupt accelerations) generally from April to September due to the influence of precipitation and reservoir scheduled level variations. With respect to many traditional machine learning techniques, two issues exist relative to displacement prediction, namely the random fluctuation of prediction results and inaccurate prediction when step-like deformations take place. In this study, a novel and original prediction method was proposed by combining the wavelet transform (WT) and particle swarm optimization-kernel extreme learning machine (PSO-KELM) methods, and by considering the landslide causal factors. A typical landslide with a step-like behavior, the Baishuihe landslide in TGRA, was taken as a case study. The cumulated total displacement was decomposed into trend displacement, periodic displacement (controlled by internal geological conditions and external triggering factors respectively), and noise. The displacement items were predicted separately by multi-factor PSO-KELM considering various causal factors, and the total displacement was obtained by summing them up. An accurate prediction was achieved by the proposed method, including the step-like deformation period. The performance of the proposed method was compared with that of the multi-factor extreme learning machine (ELM), support vector regression (SVR), backward propagation neural network (BPNN), and single-factor PSO-KELM. Results show that the PSO-KELM outperforms the other models, and the prediction accuracy can be improved by considering causal factors.     

库水变动下堆积层滑坡加卸载响应规律与稳定性预测

三峡库区堆积层滑坡稳定性受库水位变动影响十分明显,库水变动下堆积层滑坡的演化过程与稳定性预测研究对防灾减灾具有重要的指导意义。基于库水变动与滑坡变形的响应关系,建立库水动力加卸载与位移速率响应耦合的加卸载响应比预测模型;建立库水变动与滑坡稳定系数的响应关系,进而确定库水变动下滑坡体的渗流场类型,并以滑坡稳定系数的变化率的正负来判断库水变动的加卸载作用。以黄莲树滑坡为例,预测其稳定性,并对预测结果进行验证。结果表明:黄莲树滑坡水平方向位移变化与库水变动存在响应关系,且响应具有明显的滞后性;库水变动下该滑坡的渗流场属于动水压力型,每个水文年中库水动力对滑坡有6个月为加载过程,1个月为卸载过程;滑坡监测点的加卸载响应比在2011年出现整体上升并大于1,揭示滑坡趋于失稳,对库水变动加卸载作用的响应加强。结论得到了宏观变形破坏迹象的验证,说明改进的加卸载响应比预测模型具有良好的预测效果。     

Real-time monitoring and early warning of landslides at relocated Wushan Town,the Three Gorges Reservoir,China

A special monitoring and warning system has been established and improved in the Three Gorges Reservoir area since 1999. It is necessary to develop a real-time monitoring system on landslides because there are dense populations centered in the reservoir area and geo-hazards may be triggered by a 30-m water level fluctuation between 145 and 175 m in elevation during reservoir operation; the regular monitoring could not be suitable to the early warning on landslides. Since 2003, the authors have carried out a real-time monitoring and early warning project on landslides at the relocated Wushan town in the Three Gorges Reservoir area. The monitoring station includes Global Positioning System with high-accuracy double frequency to monitor ground displacement, time domain reflection technology, and immobile borehole, inclinometer to monitor deep displacement, piezometer to monitor pore water pressure, and precipitation and reservoir water level monitoring. Compared with traditional methods, the real-time monitoring is continuous and traceable in the acquisition process, and the cycle of data acquisition is very short, usually within hours, minutes, or even shorter. Based on the landslide monitoring experience at the Three Gorges Reservoir area, the early warning criteria on landslide are established in which the critical situation is classified into four levels: blue, yellow, orange, and red, respectively, expressed by no, slight, moderate, and high risk situation. Comprehensive judgment from multimonitoring data of Yuhuangge landslide in this area since 2004 suggested that the new Wushan town will be at the blue early warning level, although some monitoring data of individual displacement at deep borehole showed that the displacement was increased by 5 mm in 5 months with an average velocity of 1.0 mm/month, and the data of BOTDR also showed an obvious dislocation along a stairway on the landslide.     

基于APSO-SVR-GRU模型的白水河滑坡周期项位移预测

滑坡周期项位移的预测,是研究地质灾害中滑坡变形至关重要的一步。由于单一模型易受偶然因素影响,且无法充分利用有效信息,导致其预测精度不高,适用性不强。基于此,文中提出了一种结合自适应粒子群算法（APSO）、支持向量机回归算法（SVR）、门控神经网络算法(GRU)的组合模型。该模型通过自适应粒子群优化算法对支持向量机回归算法进行参数寻优,确定最优参数组合,然后利用最小二乘法对APSO-SVR模型与GRU模型赋权建立最优权重比组合模型。以三峡白水河滑坡作为研究对象,选取降雨量、库水位及位移量作为周期项位移的影响因子,对模型进行训练验证,结果表明:在白水河滑坡周期项位移预测中,文中所提出的APSO-SVR-GRU组合模型与单一模型相比,具有更高的预测精度和稳定性。     

Prediction of landslide displacement with step-like behavior based on multialgorithm optimization and a support vector regression model

Landslide prediction is important for mitigating geohazards but is very challenging. In landslide evolution, displacement depends on the local geological conditions and variations in the controlling factors. Such factors have led to the “step-like” deformation of landslides in the Three Gorges Reservoir area of China. Based on displacement monitoring data and the deformation characteristics of the Baishuihe Landslide, an additive time series model was established for landslide displacement prediction. In the model, cumulative displacement was divided into three parts: trend, periodic, and random terms. These terms reflect internal factors (geological environmental, gravity, etc.), external factors (rainfall, reservoir water level, etc.), and random factors (uncertainties). After statistically analyzing the displacement data, a cubic polynomial model was proposed to predict the trend term of displacement. Then, multiple algorithms were used to determine the optimal support vector regression (SVR) model and train and predict the periodic term. The results showed that the landslide displacement values predicted based on data time series and the genetic algorithm (GA-SVR) model are better than those based on grid search (GS-SVR) and particle swarm optimization (PSO-SVR) models. Finally, the random term was accurately predicted by GA-SVR. Therefore, the coupled model based on temporal data series and GA-SVR can be used to predict landslide displacement. Additionally, the GA-SVR model has broad application potential in the prediction of landslide displacement with “step-like” behavior.     

基于时间序列与人工蜂群支持向量机的滑坡位移预测研究

总结以往滑坡预测方法存在的诸多不足,针对滑坡监测位移-时间曲线特点,本文提出了一种基于时间序列的人工蜂群算法（ABC）与支持向量回归机（SVR）相结合的滑坡位移预测方法。以三峡库区白水河滑坡为例,通过对滑坡位移、降雨、库水位等因素的分析,研究影响滑坡位移变化的因素。用时间序列加法模型和移动平均法将滑坡位移分解为趋势项和周期项。以多项式最小二乘法拟合滑坡位移趋势项,用人工蜂群支持向量机模型对滑坡位移周期项进行训练和预测。通过灰色系统关联分析法计算多项因子与滑坡位移周期项之间的关联性。最终的滑坡总位移预测值为周期项预测值与趋势项预测值之和。与BP神经网络、PSO-SVR模型方法相比,该方法在滑坡位移预测中有更高的精度,在防灾减灾工作中有较好的推广应用前景。     

基于时间序列分解和多变量混沌模型的滑坡阶跃式位移预测

三峡库区某些库岸滑坡在强降雨、库水位涨落等诱发因素影响下,其位移时间序列表现出阶跃式变化特征且可能存在混沌特性.但目前常用于滑坡位移预测的混沌模型,均建立在单变量混沌理论的基础之上.且已有的考虑了诱发因素的常规多变量模型,大都采用经验性的方法来选取输入变量;常规多变量模型对滑坡位移序列的非线性特征,及其与诱发因素间的动态响应关系缺乏数学理论上的深入分析.因此,提出一种基于指数平滑法、多变量混沌模型和极限学习机（extreme learing machine,ELM）的滑坡位移组合预测模型.指数平滑多变量混沌ELM模型首先对滑坡累积位移序列的混沌特性进行识别;然后用指数平滑法对累积位移进行预测,得到趋势项位移,并用累积位移减去趋势项位移得到剩余的波动项位移;之后对波动项位移及降雨量、库水位变化量这3个因子进行多变量相空间重构,并用ELM模型对多变量重构后的波动项位移进行预测;最后将预测得到的趋势项和波动项位移值相加,得到最终的累积位移预测值.以三峡库区白水河滑坡ZG93监测点的累积位移作为实例进行分析,并将模型与指数平滑多变量混沌粒子群-支持向量机（PSO-SVM）模型、指数平滑单变量混沌ELM模型作对比.结果表明滑坡位移序列存在混沌特性,模型能有效预测滑坡位移,其预测效果优于对比模型.且本文模型从混沌理论的角度将波动项位移与降雨量、库水位变化量的动态响应关系进行综合分析,更能反映滑坡位移系统演化的物理本质.      

三峡库区浮托减重型滑坡对库水升降的响应规律

三峡大坝自2003年蓄水以来,库区形成大量涉水滑坡。长江三峡库区的浮托减重型滑坡随库水位升降,变形非协调性增加,此类滑坡变形与库水位关系的不明确性,为其监测预警预报工作带来困惑。以木鱼包滑坡为研究对象,通过全自动GPS变形监测系统获取的滑坡监测资料,结合多次的野外考察、15年专业监测和库水位升降等资料进行分析,运用有限元软件Geo-studio进行数值模拟,模拟库水位以不同速率在175~145m间升降下对滑坡稳定性的影响。研究表明:(1)库水位由145m升至175m的过程中,滑坡的稳定系数变化为先减后增再减,库水上升速率越大,前期稳定系数减小的时间段越小,随后稳定系数增加的速率也越快;(2)在库水位由175m下降到145m的过程中,整个稳定系数变化趋势为先减小后增大,呈“V”字形,存在一个最危险水面,不同的库水下降速率对应的最危险水面高度也不一样,库水位以0.4,0.6,0.8,1.0,1.6m/d的速率下降时对应的最危险水位分别在169.8,167.8,162.6,162.0,162.2m左右;(3)木鱼包滑坡作为三峡库区典型的浮托减重性滑坡,在库水位大幅度及周期性升降的影响下,一直保持着蠕滑状态,平均日位移量为0.4mm/d,目前处于基本稳定状态。所得结论对三峡库区浮托减重型滑坡预警预报工作有一定的参考与借鉴意义。     

多元时间序列分析的滑坡演化阶段划分

滑坡的时间-位移曲线一般具有3个阶段特征,即初始变形阶段、等速变形阶段和加速变形阶段,不同演化阶段加速度具有不同的变化特点.目前往往是依据对加速度曲线特征的分析来人为划分演化阶段,缺少相应的理论支持和定量计算.针对上述问题,选取月降雨量、月库水位高程变化量对滑坡的累计位移建立多因素的时间序列预测模型.然后利用Chow分割点检验理论,以所建模型中F和LR统计量最大值点作为分割点对滑坡演化阶段进行划分.以新滩滑坡和三峡库区白水河滑坡为例,利用累计位移、降雨及库水位变化数据进行计算验证.结果表明,对多元时间序列模型进行Chow分割点检验可对滑坡的演化阶段进行准确划分,为滑坡的临滑预警预报提供重要判据.      

三峡库区典型堆积层滑坡变形滞后时间效应研究

堆积层滑坡是三峡水库运行过程中的重要地质灾害,其变形演化往往滞后于库水位的变化,表现出时间滞后效应,给滑坡灾害精准预测和灾害警情准确发布造成极大困扰。采用集对分析法并结合层次分析法,构建了滑坡加权位移向量计算模型,在滑坡加权位移演化与库水位波动相互关系定性分析的基础上,寻找滑坡加权位移与库水位变化速率相关性达到最大时的平移步数,从而计算出滑坡变形滞后于库水位变化的时间。以三峡库区典型堆积层滑坡——树坪滑坡为例,在分析滑坡变形演化规律基础上,分别选取2012年、2013年、2014年汛雨期地表位移与库水位下降速率的监测数据开展滑坡变形滞后时间研究。研究发现:当库水位下降速率小于等于0.43 m·d-1时,树坪滑坡变形滞后时间大于等于5 d;当库水位下降速率在0.43 m·d-1到0.7 m·d-1之间时,树坪滑坡变形滞后时间在2 d到5 d之间;当库水位下降速率大于等于0.7 m·d-1时,树坪滑坡变形滞后时间小于等于2 d;随着库水位下降速率不断增大,树坪滑坡变形滞后时间不断缩短。通过分析滑坡不同空间位置监测点的滞后时间,发现越靠近滑坡体前缘变形滞后时间越短,当库水位下降速率在0.43 m·d-1到0.7 m·d-1之间时,滑坡前缘变形滞后时间在2.4 d到5.4 d之间,滑坡中部的变形滞后时间在3.4 d到5.6 d之间,滑坡前缘和中部的变形滞后时间差在0.2 d到1.4 d之间。研究成果可以为树坪滑坡的监测预警防治工作提供参考,对重大水利工程涉水滑坡监测预警具有一定借鉴意义。     

基于优化经验模态分解和聚类分析的滑坡位移智能预测研究

针对三峡库区"阶跃式"滑坡的变形特征,提出了一种新的滑坡位移预测方法。以白水河滑坡ZG118和XD-01监测点位移数据为例,采用基于软筛分停止准则的经验模态分解(SSSC-EMD)将累计位移-时间曲线和影响因子时间序列自适应地分解为多个固有模态函数(IMF),并采用K均值(K-Means)聚类法对其进行聚类累加,得到有物理含义的位移分量(趋势性位移、周期性位移以及随机性位移)和影响因子分量(高频影响因子和低频影响因子)。使用最小二乘法对趋势性位移进行拟合预测;采用果蝇优化-最小二乘支持向量机(FOA-LSSVM)模型对周期性位移和随机性位移进行预测。将各位移分量预测值进行叠加处理,实现滑坡累计位移的预测。研究结果表明,所提出的(SSSC-EMD)-K-Means-(FOA-LSSVM)模型能够预测"阶跃式"滑坡的位移变化规律,且预测精度高于传统的支持向量机回归(SVR)、最小二乘支持向量机(LSSVM)模型;并通过改变训练集长度,进行单因素分析,发现其与预测精度之间呈正相关关系。     

关键影响因子作用下三峡库区堆积层滑坡分布规律及变形破坏响应特征

三峡库区崩滑地质灾害频发,堆积层滑坡是最常见的滑坡类型。在分析三峡库区145处库岸堆积层滑坡资料基础上,选取地形地貌、地质岩性和斜坡构造作为控制因素、降水和库水波动作为主要诱发因素,探究堆积层滑坡在上述关键影响因子下的分布发育规律及变形破坏响应特征,阐明内在机理,结果表明:(1)受区域地质构造和基岩地层岩性显著控制,滑坡发育频次和规模沿长江存在显著空间差异性;(2)砂页岩夹煤层岩组(SC)和泥灰岩与砂泥岩互层岩组(MSM)对库区堆积层滑坡危害最大,软岩、“软-硬”互层二元结构和水-岩(土)相互作用是主导滑坡发育的主要影响因素;(3)大多数滑坡涉水,主要发育在10°~30°斜坡上,前缘高程集中在100~175 m,受库水波动影响严重,岸别和斜坡结构对堆积层滑坡发育没有明显控制作用;(4)库区滑坡主要由降雨-库水下降联合诱发滑体前缘滑移-拉裂,引发牵引式滑坡,降雨与库水波动各自对滑体的影响格局和程度存在明显差异。以期研究成果为有针对性的库区滑坡总体防治提供一定的科学指导。     

三峡库岸滑坡变形特征及影响因素分析

三峡库区涉水滑坡主要影响因素是水位和降雨量,也是库区滑坡体失稳的主要影响因素和诱发因素。库区每年重复着水位升降不利于滑坡的稳定,而降雨特别是大强度的降雨也诱发产生滑坡。当水位波动遇到降雨,出现工况叠加,滑坡将加剧。因此,有必要对影响滑坡变形的主导因素进行了解分析。2016年6月三峡库区全面展开了自动化监测,使得数据统计方便可靠。本文采用滑坡变形速率、降雨量、库水位变化、最大水位变化速率、淹没程度,运用灰色关联度分析法对涉水滑坡进行了计算分析。水位下降阶段,文中土质滑坡变形受库水位影响最大。水位上升阶段,该土质滑坡上部变形受降雨影响最大,下部受水位影响最大。文中岩质滑坡总是受库水位影响最大。     

Deformation and mechanism of landslide influenced by the effects of reservoir water and rainfall, Three Gorges, China

Since the impoundment of the Three Gorges Reservoir in June 2003, numerous preexisting landslides have been reactivated. This paper seeks to find the factors influencing landslide deformation and the relationship between displacement and fluctuation of the reservoir water level, while the displacement and the intensity of rainfall based on monitoring data; 6 years of monitoring were carried out on the Shiliushubao landslide, a old landslide, consisting of a deep-seated main block and two shallow blocks, with a volume of 1,180 × 10⁴ m³ and located on the left bank of the Yangtze River, 66 km upstream of the Three Gorges dam. This landslide was reactivated by the impoundment and since then the landslide body has been experiencing persistent deformation with an observed maximum cumulative displacement of 8,598.5 mm up to December 2009. Based on the monitoring data, we analyzed the relationship between the fluctuation of the reservoir water level and displacement, rainfall and displacement, and found that the rainfall is the major factor influencing deformation for two shallow blocks and the displacement has a positive correlation with the variation of rainfall intensity. The fluctuation of the reservoir water level is the primary factor for main block, and the deformation rate has a negative correlation with the variation of reservoir water level, declined with the rise of the water level and increased with the drawdown of the water level.     

Probabilistic forecasting of landslide displacement accounting for epistemic uncertainty: a case study in the Three Gorges Reservoir area,China

Accurate and reliable displacement forecasting plays a key role in landslide early warning. However, due to the epistemic uncertainties associated with landslide systems, errors are unavoidable and sometimes significant in traditional methods of deterministic point forecasting. Transforming traditional point forecasting into probabilistic forecasting is essential for quantifying the associated uncertainties and improving the reliability of landslide displacement forecasting. This paper proposes a hybrid approach based on bootstrap, extreme learning machine (ELM), and artificial neural network (ANN) methods to quantify the associated uncertainties via probabilistic forecasting. The hybrid approach consists of two steps. First, a bootstrap-based ELM is applied to estimate the true regression mean of landslide displacement and the corresponding variance of model uncertainties. Second, an ANN is used to estimate the variance of noise. Reliable prediction intervals (PIs) can be computed by combining the true regression mean, variance of model uncertainty, and variance of noise. The performance of the proposed hybrid approach was validated using monitoring data from the Shuping landslide, Three Gorges Reservoir area, China. The obtained results suggest that the Bootstrap-ELM-ANN approach can be used to perform probabilistic forecasting in the medium term and long term and to quantify the uncertainties associated with landslide displacement forecasting for colluvial landslides with step-like deformation in the Three Gorges Reservoir area.     

三峡库区香溪河段典型滑坡变形特征分析

本文从坡形采集入手,对三峡库区香溪河段蓄水后发生变形的滑坡进行归纳统计。统计表明,近水库岸坡为凸形的滑坡更容易发生变形。对香溪河段典型滑坡进行了长期地表位移监测,获得八字门滑坡和白家包滑坡的变形曲线为台阶状,耿家坪滑坡的变形曲线为脉动形。近库水微地貌为凸岸,滑体物质为老滑坡堆积物的滑坡变形曲线为台阶状,变形具积累性;近库水微地貌为凹岸,滑体物质为崩塌堆积物的滑坡变形曲线为脉动形,变形具“弹性”。     

基于数据挖掘技术的白水河滑坡多场信息关联准则分析

为探究滑坡多场监测数据间的关联准则,采用数据挖掘技术中的两步聚类法与Apriori算法,开展滑坡多场信息关联准则研究。以三峡库区白水河滑坡为例,分析ZG93监测点于2003年6月—2016年12月期间的监测数据,选取影响滑坡变形的主要诱发因子,采用两步聚类法对不同的影响因子进行预聚类和聚类,将数值型变量转化为离散型变量后,应用Apriori算法进行处理,生成满足最小置信度的关联准则,建立白水河滑坡多场耦合作用模式下的影响因子与滑坡位移变形关联准则判据。研究表明,关联准则对于滑坡灾害的变形分析具有重要的意义,数据挖掘技术可较好地应用于三峡库区地质灾害位移预测预报中。     

库水下降作用下滑坡动态变形机理分析以三峡库区白水河滑坡为例

在每年的库水位下降期间,三峡库区的许多滑坡都出现了较大变形。为了深入研究库水下降作用下滑坡的动态变形机理,评价和预测此类滑坡的稳定性及发展趋势,本文以白水河滑坡为例,在现场地质调查和详细地质勘查的基础上,充分利用十多年监测数据,分析其变形特征、失稳机理、影响因素及稳定性,预测了其变形发展趋势。研究结果表明在水库水位下降的过程中,由于滑坡岩土体渗透性能较差,地下水来不及及时排出,滞后于水库水位的下降,滑坡受到了坡体内地下水向外的渗透动水压力作用,从而使得滑坡稳定性降低。另外库水位下降速度越快,滑坡的位移速率也越大,表现出阶跃型动态变形特征。